© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 101806
    Prev
    Next
    INDEX
    Explanations

    Of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     formulaire
    -0.07
    显示
    -0.06
    :'+
    -0.06
    ])):↵
    -0.06
    ...↵↵↵
    -0.06
     someone
    -0.06
     їй
    -0.06
    एक
    -0.06
     Eine
    -0.06
     Refresh
    -0.06
    POSITIVE LOGITS
     assured
    0.07
     dh
    0.07
    .vertx
    0.07
    pong
    0.06
    진
    0.06
    .Config
    0.06
     vp
    0.06
    olon
    0.06
     puls
    0.06
    LOT
    0.06
    Activations Density 0.157%

    No Known Activations